Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2222 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0643. Min Act: 0.0000

Data Index: 956915 (The Pile)

Max Activating Token Index: 965

Text #1

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0545. Min Act: -0.0000

Data Index: 1206972 (The Pile)

Max Activating Token Index: 156

Text #2

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0540. Min Act: -0.0000

Data Index: 631752 (The Pile)

Max Activating Token Index: 607

Text #3

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0512. Min Act: -0.0000

Data Index: 1897022 (The Pile)

Max Activating Token Index: 685

Text #4

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0460. Min Act: -0.0000

Data Index: 6265 (The Pile)

Max Activating Token Index: 312

Text #5

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0464. Min Act: -0.0000

Data Index: 130636 (The Pile)

Max Activating Token Index: 118

Text #6

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0406. Min Act: -0.0000

Data Index: 856566 (The Pile)

Max Activating Token Index: 594

Text #7

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0404. Min Act: -0.0000

Data Index: 842604 (The Pile)

Max Activating Token Index: 733

Text #8

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0418. Min Act: -0.0000

Data Index: 267709 (The Pile)

Max Activating Token Index: 218

Text #9

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0400. Min Act: -0.0000

Data Index: 1036937 (The Pile)

Max Activating Token Index: 282

Text #10

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0413. Min Act: -0.0000

Data Index: 724883 (The Pile)

Max Activating Token Index: 288

Text #11

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0401. Min Act: -0.0000

Data Index: 1803900 (The Pile)

Max Activating Token Index: 254

Text #12

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0406. Min Act: -0.0000

Data Index: 165837 (The Pile)

Max Activating Token Index: 421

Text #13

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0377. Min Act: -0.0000

Data Index: 1501723 (The Pile)

Max Activating Token Index: 738

Text #14

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0390. Min Act: -0.0000

Data Index: 1119902 (The Pile)

Max Activating Token Index: 759

Text #15

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0369. Min Act: -0.0000

Data Index: 1119876 (The Pile)

Max Activating Token Index: 455

Text #16

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0359. Min Act: -0.0000

Data Index: 1035073 (The Pile)

Max Activating Token Index: 791

Text #17

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0354. Min Act: -0.0000

Data Index: 1934211 (The Pile)

Max Activating Token Index: 33

Text #18

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0384. Min Act: -0.0000

Data Index: 1474773 (The Pile)

Max Activating Token Index: 445

Text #19

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0367. Min Act: -0.0000

Data Index: 465650 (The Pile)

Max Activating Token Index: 66